seo-content-audit

Audit existing content across a site to decide what to keep, update, merge, redirect, or delete. Use this skill whenever the user wants to audit existing content, fix content decay, resolve keyword cannibalization, prune underperforming pages, prioritize content updates, or apply a keep/update/merge/redirect/delete framework to a content library. Triggers on content audit, content decay, content refresh, cannibalization, keyword cannibalization, prune content, delete pages, redirect old pages, content inventory, what to keep, what to update, content scorecard, evergreen refresh. Also triggers when traffic is dropping site-wide and the cause might be content quality, even if 'audit' is not said explicitly.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body that combines a metrics table, decision tree, and 7-step workflow with validation and post-audit measurement, and appropriately offloads template and cannibalization detail to two clearly-signaled reference files. Minor gains are available in tightening redundancy and adding specific data-extraction guidance.

Suggestions

Consolidate the per-action signal lists with the 'Failure patterns' section to remove overlapping restatement (e.g., backlink-checking before delete is stated in both 'Redirect signals'/'Delete signals' and the 'Deleting pages with backlinks' failure pattern).

Add concrete, copy-pasteable data-extraction steps or queries (e.g., a Search Console filter/export recipe or an example analytics segment) so the 'Pull the metrics' workflow step is executable rather than sourced by name.

Expand the workflow's validation into an explicit validate→fix→retry loop for redirect/delete batches (e.g., 'run a redirect-chain checker; if any chain breaks or loops, fix the rule and re-run before the next batch').

Dimension	Reasoning	Score
Conciseness	Lean and efficient — uses a metrics table, ASCII decision tree, and terse signal bullets without explaining basics Claude already knows; docked one point for some restatement between the per-action signals and the "Failure patterns" section.	4 / 5
Actionability	Highly concrete: a threshold table with specific low-cutoffs, an executable decision matrix, and exact spreadsheet columns/report sections; held at 4 because it names external data sources (analytics, search console, backlink tools) without specific extraction commands or API calls.	4 / 5
Workflow Clarity	A clear 7-step sequence with a validation checkpoint ("Re-crawl after each batch to confirm no broken redirect chains") and a post-audit measurement loop (30/60/90 days), satisfying the destructive/batch validation requirement; not a 5 because validation is terse rather than a full validate→fix→retry loop with error-recovery detail.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview that splits detail into two one-level-deep, clearly-signaled reference files (audit-template.md, cannibalization-resolution.md), both of which exist and are linked with descriptions — easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states the five-action framework and supplies a rich, natural set of trigger phrases covering both explicit audit requests and the implicit traffic-decline case. It explicitly answers what and when with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and five concrete actions — "keep, update, merge, redirect, or delete" — matching the comprehensive-coverage anchor; no generic filler.	5 / 5
Completeness	Explicitly answers both "what" (audit content and assign one of five decisions) and "when" ("Use this skill whenever...", "Triggers on...", "Also triggers when traffic is dropping site-wide...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases including synonyms ("content audit, content decay, content refresh, cannibalization, keyword cannibalization, prune content, delete pages, redirect old pages, content inventory, what to keep, what to update, content scorecard, evergreen refresh") plus an implicit site-wide-traffic-drop trigger.	5 / 5
Distinctiveness Conflict Risk	The keep/update/merge/redirect/delete framework carves a clear, distinctive niche; the only slight overlap risk (site-wide traffic drop) is scoped to content-quality causes, keeping conflict minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rampstackco/claude-skills
Path: skills/seo-content-audit/SKILL.md
Commit: 0479242

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.